Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical specifications and URLs related to various applications or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Values assigned with "=" or "=$" appearing after identifiers

    np_acts-logits-general · gemini-2.0-flash

    identifier =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.54
    ↵↵
    -0.54
    .
    -0.50
    ,
    -0.47
     
    -0.47
     therefore
    -0.46
     "
    -0.45
    ↵
    -0.43
      
    -0.42
     (
    -0.42
    POSITIVE LOGITS
    +#+#
    1.05
    =
    0.97
     Efq
    0.93
    DockStyle
    0.91
    GraphicsUnit
    0.90
    出版年
    0.88
     myſelf
    0.86
     TextInputType
    0.85
     MainAxisSize
    0.84
    ruptedException
    0.83
    Act Density 0.293%

    No Known Activations